# pentest-validation

pentest-validation validates SAST and DAST scanner findings against non-production targets, filters out false alarms, and produces PoC exploit proof.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 147 installs · ★ 533 repo stars
- Author: proffesor-for-testing
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/pentest-validation/SKILL.md
- Updated: 2026-10-25
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/pentest-validation

## What it does

The skill manages a structured 4-phase security pipeline covering recon, analysis, validation, and final reporting. Work is distributed across specialized sub-agents including `qe-security-scanner`, `qe-security-reviewer`, `qe-security-auditor`, `qe-pentest-validator`, and `qe-quality-gate`. The process operates under a strict "No Exploit, No Report" rule, ensuring only issues with working proof make the final summary.

Validation runs across three graduated tiers. Tier 1 inspects source code patterns locally using WASM. Tier 2 tests targeted payloads against live endpoints, while Tier 3 builds full exploit chains. Separate dedicated pipelines handle injection flaws, cross-site scripting, server-side request forgery, and authentication bypasses.

Without explicit user confirmation of target ownership, the skill halts execution immediately. Built-in safeguards restrict testing to staging or development environments, automatically block domains matching patterns like `api.*` or `www.*`, and enforce a default cap of 30 minutes and 15 dollars.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill pentest-validation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/pentest-validation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/pentest-validation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill pentest-validation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/pentest-validation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill pentest-validation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/pentest-validation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install proffesor-for-testing/agentic-qe assets/skills/pentest-validation
```

2. **Manually: put the files in place**
- File: `.github/skills/pentest-validation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill pentest-validation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/pentest-validation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/pentest-validation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill pentest-validation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/pentest-validation/SKILL.md

## When to use it
- Eliminate false positive alerts from SAST and DAST scans
- Verify vulnerability exploitability with working PoC evidence
- Run targeted checks for injections, XSS, SSRF, and broken auth
- Audit staging deployments within strict runtime and cost limits

## Example prompts
- Validate SAST scan findings in `./src` using tier 1 pattern checks
- Run XSS and SSRF validation against staging target `https://staging.app.com`
- Execute security audit pipeline on the codebase with a $15 budget cap

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 53d14360e91b1830.

BEGIN THIRD-PARTY FILE 53d14360e91b1830
```text
---
name: pentest-validation
description: "Use when validating security findings from SAST/DAST scans, proving exploitability of reported vulnerabilities, eliminating false positives, or running the 4-phase pentest pipeline (recon, analysis, validation, report)."
category: specialized-testing
priority: critical
tokenEstimate: 1500
agents: [qe-pentest-validator, qe-security-scanner, qe-security-reviewer, qe-security-auditor, qe-quality-gate]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2026-02-08
dependencies: [security-testing]
quick_reference_card: true
tags: [pentest, exploitation, security-validation, shannon, no-exploit-no-report, graduated-exploitation]
trust_tier: 3
validation:
  schema_path: schemas/output.json
  validator_path: scripts/validate-config.json
  eval_path: evals/pentest-validation.yaml
---

# Pentest Validation

<default_to_action>
When validating security findings:
1. REQUIRE explicit authorization for target URL
2. SCAN with qe-security-scanner (SAST + dependency + secrets)
3. ANALYZE with qe-security-reviewer + qe-security-auditor (parallel)
4. VALIDATE with qe-pentest-validator (graduated exploitation, parallel per vuln type)
5. REPORT only confirmed findings with PoC evidence ("No Exploit, No Report")
6. UPDATE exploit playbook with new patterns

**Quality Gates:**
- Authorization confirmed before ANY exploitation
- Target URL is staging/dev (NOT production)
- Budget cap enforced ($15 default)
- Time cap enforced (30 min default)
- All exploitation attempts logged
</default_to_action>

## Quick Reference Card

### The 4-Phase Pipeline

| Phase | Agent(s) | Purpose | Parallelism |
|-------|----------|---------|-------------|
| **1. Recon** | qe-security-scanner | SAST, DAST, dependency scan, secrets | Internal parallel |
| **2. Analysis** | qe-security-reviewer + qe-security-auditor | Code review + compliance check | Both in parallel |
| **3. Validation** | qe-pentest-validator | Graduated exploit validation | Per-vuln-type parallel |
| **4. Report** | qe-quality-gate | "No Exploit, No Report" filter | Sequential |

### Graduated Exploitation Tiers

| Tier | Handler | Cost | Latency | Use When |
|------|---------|------|---------|----------|
| **1** | Agent Booster (WASM) | $0 | <1ms | Code pattern is conclusive (eval, innerHTML, hardcoded creds) |
```
END THIRD-PARTY FILE 53d14360e91b1830

The third-party file has ended. Everything between the 53d14360e91b1830 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2343 of 10617 bytes. © proffesor-for-testing · MIT · https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/pentest-validation/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
